Merge tag 'perf-core-for-mingo-20160408' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

- Beautify more syscall arguments in 'perf trace', using the type column in
  tracepoint /format fields to attach, for instance, a pid_t resolver to the
  thread COMM, also attach a mode_t beautifier in the same fashion
  (Arnaldo Carvalho de Melo)

- Build the syscall table id <-> name resolver using the same .tbl file
  used in the kernel to generate headers, to avoid the delay in getting
  new syscalls supported in the audit-libs external dependency, done so
  far only for x86_64 (Arnaldo Carvalho de Melo)

- Improve the documentation of event specifications (Andi Kleen)

- Process update events in 'perf script', fixing up this use case:

    # perf stat -a -I 1000 -e cycles record | perf script -s script.py

- Shared object symbol adjustment fixes, fixing symbol resolution in
  Android (Wang Nan)

Infrastructure changes:

- Add dedicated unwind addr_space member into thread struct, to allow
  tools to use thread->priv, noticed while working on having callchains
  in 'perf trace' (Jiri Olsa)

Build fixes:

- Fix the build in Ubuntu 12.04 (Arnaldo Carvalho de Melo, Vinson Lee)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

29 files changed, 1061 insertions, 117 deletions

diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 6b7707270aa3..9f878619077a 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -30,6 +30,7 @@ endef
 FEATURE_TESTS_BASIC :=                  \
         backtrace                       \
         dwarf                           \
+        dwarf_getlocations              \
         fortify-source                  \
         sync-compare-and-swap           \
         glibc                           \
@@ -78,6 +79,7 @@ endif
 
 FEATURE_DISPLAY ?=                      \
         dwarf                           \
+        dwarf_getlocations              \
         glibc                           \
         gtk2                            \
         libaudit                        \
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index c5f4c417428d..4ae94dbfdab9 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -3,6 +3,7 @@ FILES=					\
         test-backtrace.bin              \
         test-bionic.bin                 \
         test-dwarf.bin                  \
+        test-dwarf_getlocations.bin     \
         test-fortify-source.bin         \
         test-sync-compare-and-swap.bin  \
         test-glibc.bin                  \
@@ -82,6 +83,9 @@ endif
 $(OUTPUT)test-dwarf.bin:
         $(BUILD) $(DWARFLIBS)
 
+$(OUTPUT)test-dwarf_getlocations.bin:
+        $(BUILD) $(DWARFLIBS)
+
 $(OUTPUT)test-libelf-mmap.bin:
         $(BUILD) -lelf
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index e499a36c1e4a..a282e8cb84f3 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -41,6 +41,10 @@
 # include "test-dwarf.c"
 #undef main
 
+#define main main_test_dwarf_getlocations
+# include "test-dwarf_getlocations.c"
+#undef main
+
 #define main main_test_libelf_getphdrnum
 # include "test-libelf-getphdrnum.c"
 #undef main
@@ -143,6 +147,7 @@ int main(int argc, char *argv[])
         main_test_libelf_mmap();
         main_test_glibc();
         main_test_dwarf();
+        main_test_dwarf_getlocations();
         main_test_libelf_getphdrnum();
         main_test_libunwind();
         main_test_libaudit();
diff --git a/tools/build/feature/test-dwarf_getlocations.c b/tools/build/feature/test-dwarf_getlocations.c
new file mode 100644
index 000000000000..70162699dd43
--- /dev/null
+++ b/tools/build/feature/test-dwarf_getlocations.c
@@ -0,0 +1,12 @@
+#include <stdlib.h>
+#include <elfutils/libdw.h>
+
+int main(void)
+{
+        Dwarf_Addr base, start, end;
+        Dwarf_Attribute attr;
+        Dwarf_Op *op;
+        size_t nops;
+        ptrdiff_t offset = 0;
+        return (int)dwarf_getlocations(&attr, offset, &base, &start, &end, &op, &nops);
+}
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index ec723d0a5bb3..a126e97a8114 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -93,6 +93,67 @@ raw encoding of 0x1A8 can be used:
 You should refer to the processor specific documentation for getting these
 details. Some of them are referenced in the SEE ALSO section below.
 
+ARBITRARY PMUS
+--------------
+
+perf also supports an extended syntax for specifying raw parameters
+to PMUs. Using this typically requires looking up the specific event
+in the CPU vendor specific documentation.
+
+The available PMUs and their raw parameters can be listed with
+
+  ls /sys/devices/*/format
+
+For example the raw event "LSD.UOPS" core pmu event above could
+be specified as
+
+  perf stat -e cpu/event=0xa8,umask=0x1,name=LSD.UOPS_CYCLES,cmask=1/ ...
+
+PER SOCKET PMUS
+---------------
+
+Some PMUs are not associated with a core, but with a whole CPU socket.
+Events on these PMUs generally cannot be sampled, but only counted globally
+with perf stat -a. They can be bound to one logical CPU, but will measure
+all the CPUs in the same socket.
+
+This example measures memory bandwidth every second
+on the first memory controller on socket 0 of a Intel Xeon system
+
+  perf stat -C 0 -a uncore_imc_0/cas_count_read/,uncore_imc_0/cas_count_write/ -I 1000 ...
+
+Each memory controller has its own PMU.  Measuring the complete system
+bandwidth would require specifying all imc PMUs (see perf list output),
+and adding the values together.
+
+This example measures the combined core power every second
+
+  perf stat -I 1000 -e power/energy-cores/  -a
+
+ACCESS RESTRICTIONS
+-------------------
+
+For non root users generally only context switched PMU events are available.
+This is normally only the events in the cpu PMU, the predefined events
+like cycles and instructions and some software events.
+
+Other PMUs and global measurements are normally root only.
+Some event qualifiers, such as "any", are also root only.
+
+This can be overriden by setting the kernel.perf_event_paranoid
+sysctl to -1, which allows non root to use these events.
+
+For accessing trace point events perf needs to have read access to
+/sys/kernel/debug/tracing, even when perf_event_paranoid is in a relaxed
+setting.
+
+TRACING
+-------
+
+Some PMUs control advanced hardware tracing capabilities, such as Intel PT,
+that allows low overhead execution tracing.  These are described in a separate
+intel-pt.txt document.
+
 PARAMETERIZED EVENTS
 --------------------
 
@@ -106,6 +167,50 @@ also be supplied. For example:
 
   perf stat -C 0 -e 'hv_gpci/dtbp_ptitc,phys_processor_idx=0x2/' ...
 
+EVENT GROUPS
+------------
+
+Perf supports time based multiplexing of events, when the number of events
+active exceeds the number of hardware performance counters. Multiplexing
+can cause measurement errors when the workload changes its execution
+profile.
+
+When metrics are computed using formulas from event counts, it is useful to
+ensure some events are always measured together as a group to minimize multiplexing
+errors. Event groups can be specified using { }.
+
+  perf stat -e '{instructions,cycles}' ...
+
+The number of available performance counters depend on the CPU. A group
+cannot contain more events than available counters.
+For example Intel Core CPUs typically have four generic performance counters
+for the core, plus three fixed counters for instructions, cycles and
+ref-cycles. Some special events have restrictions on which counter they
+can schedule, and may not support multiple instances in a single group.
+When too many events are specified in the group none of them will not
+be measured.
+
+Globally pinned events can limit the number of counters available for
+other groups. On x86 systems, the NMI watchdog pins a counter by default.
+The nmi watchdog can be disabled as root with
+
+        echo 0 > /proc/sys/kernel/nmi_watchdog
+
+Events from multiple different PMUs cannot be mixed in a group, with
+some exceptions for software events.
+
+LEADER SAMPLING
+---------------
+
+perf also supports group leader sampling using the :S specifier.
+
+  perf record -e '{cycles,instructions}:S' ...
+  perf report --group
+
+Normally all events in a event group sample, but with :S only
+the first event (the leader) samples, and it only reads the values of the
+other events in the group.
+
 OPTIONS
 -------
 
@@ -143,5 +248,5 @@ SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-top[1],
 linkperf:perf-record[1],
-http://www.intel.com/Assets/PDF/manual/253669.pdf[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide],
+http://www.intel.com/sdm/[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide],
 http://support.amd.com/us/Processor_TechDocs/24593_APM_v2.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming]
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 000ea210389d..bde8cbae7dd9 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -183,6 +183,11 @@ endif
 include config/Makefile
 endif
 
+ifeq ($(config),0)
+include $(srctree)/tools/scripts/Makefile.arch
+-include arch/$(ARCH)/Makefile
+endif
+
 # The FEATURE_DUMP_EXPORT holds location of the actual
 # FEATURE_DUMP file to be used to bypass feature detection
 # (for bpf or any other subproject)
@@ -297,8 +302,6 @@ endif
 # because maintaining the nesting to match is a pain.  If
 # we had "elif" things would have been much nicer...
 
--include arch/$(ARCH)/Makefile
-
 ifneq ($(OUTPUT),)
   CFLAGS += -I$(OUTPUT)
 endif
@@ -390,7 +393,7 @@ endif
 __build-dir = $(subst $(OUTPUT),,$(dir $@))
 build-dir   = $(if $(__build-dir),$(__build-dir),.)
 
-prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h fixdep
+prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h fixdep archheaders
 
 $(OUTPUT)%.o: %.c prepare FORCE
         $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
@@ -430,7 +433,7 @@ $(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h)
 
 LIBPERF_IN := $(OUTPUT)libperf-in.o
 
-$(LIBPERF_IN): fixdep FORCE
+$(LIBPERF_IN): prepare fixdep FORCE
         $(Q)$(MAKE) $(build)=libperf
 
 $(LIB_FILE): $(LIBPERF_IN)
@@ -625,7 +628,7 @@ config-clean:
         $(call QUIET_CLEAN, config)
         $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null
 
-clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean
+clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean
         $(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
         $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
         $(Q)$(RM) $(OUTPUT).config-detected
@@ -662,5 +665,5 @@ FORCE:
 .PHONY: all install clean config-clean strip install-gtk
 .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
 .PHONY: $(GIT-HEAD-PHONY) TAGS tags cscope FORCE prepare
-.PHONY: libtraceevent_plugins
+.PHONY: libtraceevent_plugins archheaders
 
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 269af2143735..a33729173b13 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -4,3 +4,26 @@ endif
 HAVE_KVM_STAT_SUPPORT := 1
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 PERF_HAVE_JITDUMP := 1
+
+###
+# Syscall table generation
+#
+
+out    := $(OUTPUT)arch/x86/include/generated/asm
+header := $(out)/syscalls_64.c
+sys    := $(srctree)/tools/perf/arch/x86/entry/syscalls
+systbl := $(sys)/syscalltbl.sh
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
+
+$(header): $(sys)/syscall_64.tbl $(systbl)
+        @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
+        (diff -B arch/x86/entry/syscalls/syscall_64.tbl ../../arch/x86/entry/syscalls/syscall_64.tbl >/dev/null) \
+        || echo "Warning: x86_64's syscall_64.tbl differs from kernel" >&2 )) || true
+        $(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@
+
+clean::
+        rm -f $(header)
+
+archheaders: $(header)
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
new file mode 100644
index 000000000000..2e5b565adacc
--- /dev/null
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -0,0 +1,374 @@
+#
+# 64-bit system call numbers and entry vectors
+#
+# The format is:
+# <number> <abi> <name> <entry point>
+#
+# The abi is "common", "64" or "x32" for this file.
+#
+0       common  read                    sys_read
+1       common  write                   sys_write
+2       common  open                    sys_open
+3       common  close                   sys_close
+4       common  stat                    sys_newstat
+5       common  fstat                   sys_newfstat
+6       common  lstat                   sys_newlstat
+7       common  poll                    sys_poll
+8       common  lseek                   sys_lseek
+9       common  mmap                    sys_mmap
+10      common  mprotect                sys_mprotect
+11      common  munmap                  sys_munmap
+12      common  brk                     sys_brk
+13      64      rt_sigaction            sys_rt_sigaction
+14      common  rt_sigprocmask          sys_rt_sigprocmask
+15      64      rt_sigreturn            sys_rt_sigreturn/ptregs
+16      64      ioctl                   sys_ioctl
+17      common  pread64                 sys_pread64
+18      common  pwrite64                sys_pwrite64
+19      64      readv                   sys_readv
+20      64      writev                  sys_writev
+21      common  access                  sys_access
+22      common  pipe                    sys_pipe
+23      common  select                  sys_select
+24      common  sched_yield             sys_sched_yield
+25      common  mremap                  sys_mremap
+26      common  msync                   sys_msync
+27      common  mincore                 sys_mincore
+28      common  madvise                 sys_madvise
+29      common  shmget                  sys_shmget
+30      common  shmat                   sys_shmat
+31      common  shmctl                  sys_shmctl
+32      common  dup                     sys_dup
+33      common  dup2                    sys_dup2
+34      common  pause                   sys_pause
+35      common  nanosleep               sys_nanosleep
+36      common  getitimer               sys_getitimer
+37      common  alarm                   sys_alarm
+38      common  setitimer               sys_setitimer
+39      common  getpid                  sys_getpid
+40      common  sendfile                sys_sendfile64
+41      common  socket                  sys_socket
+42      common  connect                 sys_connect
+43      common  accept                  sys_accept
+44      common  sendto                  sys_sendto
+45      64      recvfrom                sys_recvfrom
+46      64      sendmsg                 sys_sendmsg
+47      64      recvmsg                 sys_recvmsg
+48      common  shutdown                sys_shutdown
+49      common  bind                    sys_bind
+50      common  listen                  sys_listen
+51      common  getsockname             sys_getsockname
+52      common  getpeername             sys_getpeername
+53      common  socketpair              sys_socketpair
+54      64      setsockopt              sys_setsockopt
+55      64      getsockopt              sys_getsockopt
+56      common  clone                   sys_clone/ptregs
+57      common  fork                    sys_fork/ptregs
+58      common  vfork                   sys_vfork/ptregs
+59      64      execve                  sys_execve/ptregs
+60      common  exit                    sys_exit
+61      common  wait4                   sys_wait4
+62      common  kill                    sys_kill
+63      common  uname                   sys_newuname
+64      common  semget                  sys_semget
+65      common  semop                   sys_semop
+66      common  semctl                  sys_semctl
+67      common  shmdt                   sys_shmdt
+68      common  msgget                  sys_msgget
+69      common  msgsnd                  sys_msgsnd
+70      common  msgrcv                  sys_msgrcv
+71      common  msgctl                  sys_msgctl
+72      common  fcntl                   sys_fcntl
+73      common  flock                   sys_flock
+74      common  fsync                   sys_fsync
+75      common  fdatasync               sys_fdatasync
+76      common  truncate                sys_truncate
+77      common  ftruncate               sys_ftruncate
+78      common  getdents                sys_getdents
+79      common  getcwd                  sys_getcwd
+80      common  chdir                   sys_chdir
+81      common  fchdir                  sys_fchdir
+82      common  rename                  sys_rename
+83      common  mkdir                   sys_mkdir
+84      common  rmdir                   sys_rmdir
+85      common  creat                   sys_creat
+86      common  link                    sys_link
+87      common  unlink                  sys_unlink
+88      common  symlink                 sys_symlink
+89      common  readlink                sys_readlink
+90      common  chmod                   sys_chmod
+91      common  fchmod                  sys_fchmod
+92      common  chown                   sys_chown
+93      common  fchown                  sys_fchown
+94      common  lchown                  sys_lchown
+95      common  umask                   sys_umask
+96      common  gettimeofday            sys_gettimeofday
+97      common  getrlimit               sys_getrlimit
+98      common  getrusage               sys_getrusage
+99      common  sysinfo                 sys_sysinfo
+100     common  times                   sys_times
+101     64      ptrace                  sys_ptrace
+102     common  getuid                  sys_getuid
+103     common  syslog                  sys_syslog
+104     common  getgid                  sys_getgid
+105     common  setuid                  sys_setuid
+106     common  setgid                  sys_setgid
+107     common  geteuid                 sys_geteuid
+108     common  getegid                 sys_getegid
+109     common  setpgid                 sys_setpgid
+110     common  getppid                 sys_getppid
+111     common  getpgrp                 sys_getpgrp
+112     common  setsid                  sys_setsid
+113     common  setreuid                sys_setreuid
+114     common  setregid                sys_setregid
+115     common  getgroups               sys_getgroups
+116     common  setgroups               sys_setgroups
+117     common  setresuid               sys_setresuid
+118     common  getresuid               sys_getresuid
+119     common  setresgid               sys_setresgid
+120     common  getresgid               sys_getresgid
+121     common  getpgid                 sys_getpgid
+122     common  setfsuid                sys_setfsuid
+123     common  setfsgid                sys_setfsgid
+124     common  getsid                  sys_getsid
+125     common  capget                  sys_capget
+126     common  capset                  sys_capset
+127     64      rt_sigpending           sys_rt_sigpending
+128     64      rt_sigtimedwait         sys_rt_sigtimedwait
+129     64      rt_sigqueueinfo         sys_rt_sigqueueinfo
+130     common  rt_sigsuspend           sys_rt_sigsuspend
+131     64      sigaltstack             sys_sigaltstack
+132     common  utime                   sys_utime
+133     common  mknod                   sys_mknod
+134     64      uselib
+135     common  personality             sys_personality
+136     common  ustat                   sys_ustat
+137     common  statfs                  sys_statfs
+138     common  fstatfs                 sys_fstatfs
+139     common  sysfs                   sys_sysfs
+140     common  getpriority             sys_getpriority
+141     common  setpriority             sys_setpriority
+142     common  sched_setparam          sys_sched_setparam
+143     common  sched_getparam          sys_sched_getparam
+144     common  sched_setscheduler      sys_sched_setscheduler
+145     common  sched_getscheduler      sys_sched_getscheduler
+146     common  sched_get_priority_max  sys_sched_get_priority_max
+147     common  sched_get_priority_min  sys_sched_get_priority_min
+148     common  sched_rr_get_interval   sys_sched_rr_get_interval
+149     common  mlock                   sys_mlock
+150     common  munlock                 sys_munlock
+151     common  mlockall                sys_mlockall
+152     common  munlockall              sys_munlockall
+153     common  vhangup                 sys_vhangup
+154     common  modify_ldt              sys_modify_ldt
+155     common  pivot_root              sys_pivot_root
+156     64      _sysctl                 sys_sysctl
+157     common  prctl                   sys_prctl
+158     common  arch_prctl              sys_arch_prctl
+159     common  adjtimex                sys_adjtimex
+160     common  setrlimit               sys_setrlimit
+161     common  chroot                  sys_chroot
+162     common  sync                    sys_sync
+163     common  acct                    sys_acct
+164     common  settimeofday            sys_settimeofday
+165     common  mount                   sys_mount
+166     common  umount2                 sys_umount
+167     common  swapon                  sys_swapon
+168     common  swapoff                 sys_swapoff
+169     common  reboot                  sys_reboot
+170     common  sethostname             sys_sethostname
+171     common  setdomainname           sys_setdomainname
+172     common  iopl                    sys_iopl/ptregs
+173     common  ioperm                  sys_ioperm
+174     64      create_module
+175     common  init_module             sys_init_module
+176     common  delete_module           sys_delete_module
+177     64      get_kernel_syms
+178     64      query_module
+179     common  quotactl                sys_quotactl
+180     64      nfsservctl
+181     common  getpmsg
+182     common  putpmsg
+183     common  afs_syscall
+184     common  tuxcall
+185     common  security
+186     common  gettid                  sys_gettid
+187     common  readahead               sys_readahead
+188     common  setxattr                sys_setxattr
+189     common  lsetxattr               sys_lsetxattr
+190     common  fsetxattr               sys_fsetxattr
+191     common  getxattr                sys_getxattr
+192     common  lgetxattr               sys_lgetxattr
+193     common  fgetxattr               sys_fgetxattr
+194     common  listxattr               sys_listxattr
+195     common  llistxattr              sys_llistxattr
+196     common  flistxattr              sys_flistxattr
+197     common  removexattr             sys_removexattr
+198     common  lremovexattr            sys_lremovexattr
+199     common  fremovexattr            sys_fremovexattr
+200     common  tkill                   sys_tkill
+201     common  time                    sys_time
+202     common  futex                   sys_futex
+203     common  sched_setaffinity       sys_sched_setaffinity
+204     common  sched_getaffinity       sys_sched_getaffinity
+205     64      set_thread_area
+206     64      io_setup                sys_io_setup
+207     common  io_destroy              sys_io_destroy
+208     common  io_getevents            sys_io_getevents
+209     64      io_submit               sys_io_submit
+210     common  io_cancel               sys_io_cancel
+211     64      get_thread_area
+212     common  lookup_dcookie          sys_lookup_dcookie
+213     common  epoll_create            sys_epoll_create
+214     64      epoll_ctl_old
+215     64      epoll_wait_old
+216     common  remap_file_pages        sys_remap_file_pages
+217     common  getdents64              sys_getdents64
+218     common  set_tid_address         sys_set_tid_address
+219     common  restart_syscall         sys_restart_syscall
+220     common  semtimedop              sys_semtimedop
+221     common  fadvise64               sys_fadvise64
+222     64      timer_create            sys_timer_create
+223     common  timer_settime           sys_timer_settime
+224     common  timer_gettime           sys_timer_gettime
+225     common  timer_getoverrun        sys_timer_getoverrun
+226     common  timer_delete            sys_timer_delete
+227     common  clock_settime           sys_clock_settime
+228     common  clock_gettime           sys_clock_gettime
+229     common  clock_getres            sys_clock_getres
+230     common  clock_nanosleep         sys_clock_nanosleep
+231     common  exit_group              sys_exit_group
+232     common  epoll_wait              sys_epoll_wait
+233     common  epoll_ctl               sys_epoll_ctl
+234     common  tgkill                  sys_tgkill
+235     common  utimes                  sys_utimes
+236     64      vserver
+237     common  mbind                   sys_mbind
+238     common  set_mempolicy           sys_set_mempolicy
+239     common  get_mempolicy           sys_get_mempolicy
+240     common  mq_open                 sys_mq_open
+241     common  mq_unlink               sys_mq_unlink
+242     common  mq_timedsend            sys_mq_timedsend
+243     common  mq_timedreceive         sys_mq_timedreceive
+244     64      mq_notify               sys_mq_notify
+245     common  mq_getsetattr           sys_mq_getsetattr
+246     64      kexec_load              sys_kexec_load
+247     64      waitid                  sys_waitid
+248     common  add_key                 sys_add_key
+249     common  request_key             sys_request_key
+250     common  keyctl                  sys_keyctl
+251     common  ioprio_set              sys_ioprio_set
+252     common  ioprio_get              sys_ioprio_get
+253     common  inotify_init            sys_inotify_init
+254     common  inotify_add_watch       sys_inotify_add_watch
+255     common  inotify_rm_watch        sys_inotify_rm_watch
+256     common  migrate_pages           sys_migrate_pages
+257     common  openat                  sys_openat
+258     common  mkdirat                 sys_mkdirat
+259     common  mknodat                 sys_mknodat
+260     common  fchownat                sys_fchownat
+261     common  futimesat               sys_futimesat
+262     common  newfstatat              sys_newfstatat
+263     common  unlinkat                sys_unlinkat
+264     common  renameat                sys_renameat
+265     common  linkat                  sys_linkat
+266     common  symlinkat               sys_symlinkat
+267     common  readlinkat              sys_readlinkat
+268     common  fchmodat                sys_fchmodat
+269     common  faccessat               sys_faccessat
+270     common  pselect6                sys_pselect6
+271     common  ppoll                   sys_ppoll
+272     common  unshare                 sys_unshare
+273     64      set_robust_list         sys_set_robust_list
+274     64      get_robust_list         sys_get_robust_list
+275     common  splice                  sys_splice
+276     common  tee                     sys_tee
+277     common  sync_file_range         sys_sync_file_range
+278     64      vmsplice                sys_vmsplice
+279     64      move_pages              sys_move_pages
+280     common  utimensat               sys_utimensat
+281     common  epoll_pwait             sys_epoll_pwait
+282     common  signalfd                sys_signalfd
+283     common  timerfd_create          sys_timerfd_create
+284     common  eventfd                 sys_eventfd
+285     common  fallocate               sys_fallocate
+286     common  timerfd_settime         sys_timerfd_settime
+287     common  timerfd_gettime         sys_timerfd_gettime
+288     common  accept4                 sys_accept4
+289     common  signalfd4               sys_signalfd4
+290     common  eventfd2                sys_eventfd2
+291     common  epoll_create1           sys_epoll_create1
+292     common  dup3                    sys_dup3
+293     common  pipe2                   sys_pipe2
+294     common  inotify_init1           sys_inotify_init1
+295     64      preadv                  sys_preadv
+296     64      pwritev                 sys_pwritev
+297     64      rt_tgsigqueueinfo       sys_rt_tgsigqueueinfo
+298     common  perf_event_open         sys_perf_event_open
+299     64      recvmmsg                sys_recvmmsg
+300     common  fanotify_init           sys_fanotify_init
+301     common  fanotify_mark           sys_fanotify_mark
+302     common  prlimit64               sys_prlimit64
+303     common  name_to_handle_at       sys_name_to_handle_at
+304     common  open_by_handle_at       sys_open_by_handle_at
+305     common  clock_adjtime           sys_clock_adjtime
+306     common  syncfs                  sys_syncfs
+307     64      sendmmsg                sys_sendmmsg
+308     common  setns                   sys_setns
+309     common  getcpu                  sys_getcpu
+310     64      process_vm_readv        sys_process_vm_readv
+311     64      process_vm_writev       sys_process_vm_writev
+312     common  kcmp                    sys_kcmp
+313     common  finit_module            sys_finit_module
+314     common  sched_setattr           sys_sched_setattr
+315     common  sched_getattr           sys_sched_getattr
+316     common  renameat2               sys_renameat2
+317     common  seccomp                 sys_seccomp
+318     common  getrandom               sys_getrandom
+319     common  memfd_create            sys_memfd_create
+320     common  kexec_file_load         sys_kexec_file_load
+321     common  bpf                     sys_bpf
+322     64      execveat                sys_execveat/ptregs
+323     common  userfaultfd             sys_userfaultfd
+324     common  membarrier              sys_membarrier
+325     common  mlock2                  sys_mlock2
+326     common  copy_file_range         sys_copy_file_range
+
+#
+# x32-specific system call numbers start at 512 to avoid cache impact
+# for native 64-bit operation.
+#
+512     x32     rt_sigaction            compat_sys_rt_sigaction
+513     x32     rt_sigreturn            sys32_x32_rt_sigreturn
+514     x32     ioctl                   compat_sys_ioctl
+515     x32     readv                   compat_sys_readv
+516     x32     writev                  compat_sys_writev
+517     x32     recvfrom                compat_sys_recvfrom
+518     x32     sendmsg                 compat_sys_sendmsg
+519     x32     recvmsg                 compat_sys_recvmsg
+520     x32     execve                  compat_sys_execve/ptregs
+521     x32     ptrace                  compat_sys_ptrace
+522     x32     rt_sigpending           compat_sys_rt_sigpending
+523     x32     rt_sigtimedwait         compat_sys_rt_sigtimedwait
+524     x32     rt_sigqueueinfo         compat_sys_rt_sigqueueinfo
+525     x32     sigaltstack             compat_sys_sigaltstack
+526     x32     timer_create            compat_sys_timer_create
+527     x32     mq_notify               compat_sys_mq_notify
+528     x32     kexec_load              compat_sys_kexec_load
+529     x32     waitid                  compat_sys_waitid
+530     x32     set_robust_list         compat_sys_set_robust_list
+531     x32     get_robust_list         compat_sys_get_robust_list
+532     x32     vmsplice                compat_sys_vmsplice
+533     x32     move_pages              compat_sys_move_pages
+534     x32     preadv                  compat_sys_preadv64
+535     x32     pwritev                 compat_sys_pwritev64
+536     x32     rt_tgsigqueueinfo       compat_sys_rt_tgsigqueueinfo
+537     x32     recvmmsg                compat_sys_recvmmsg
+538     x32     sendmmsg                compat_sys_sendmmsg
+539     x32     process_vm_readv        compat_sys_process_vm_readv
+540     x32     process_vm_writev       compat_sys_process_vm_writev
+541     x32     setsockopt              compat_sys_setsockopt
+542     x32     getsockopt              compat_sys_getsockopt
+543     x32     io_setup                compat_sys_io_setup
+544     x32     io_submit               compat_sys_io_submit
+545     x32     execveat                compat_sys_execveat/ptregs
diff --git a/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh b/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh
new file mode 100755
index 000000000000..49a18b9ad9cf
--- /dev/null
+++ b/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh
@@ -0,0 +1,39 @@
+#!/bin/sh
+
+in="$1"
+arch="$2"
+
+syscall_macro() {
+    nr="$1"
+    name="$2"
+
+    echo "      [$nr] = \"$name\","
+}
+
+emit() {
+    nr="$1"
+    entry="$2"
+
+    syscall_macro "$nr" "$entry"
+}
+
+echo "static const char *syscalltbl_${arch}[] = {"
+
+sorted_table=$(mktemp /tmp/syscalltbl.XXXXXX)
+grep '^[0-9]' "$in" | sort -n > $sorted_table
+
+max_nr=0
+while read nr abi name entry compat; do
+    if [ $nr -ge 512 ] ; then # discard compat sycalls
+        break
+    fi
+
+    emit "$nr" "$name"
+    max_nr=$nr
+done < $sorted_table
+
+rm -f $sorted_table
+
+echo "};"
+
+echo "#define SYSCALLTBL_${arch}_MAX_ID ${max_nr}"
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 3770c3dffe5e..59009aa7e2ca 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1961,6 +1961,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
                         .exit            = perf_event__process_exit,
                         .fork            = perf_event__process_fork,
                         .attr            = process_attr,
+                        .event_update   = perf_event__process_event_update,
                         .tracing_data    = perf_event__process_tracing_data,
                         .build_id        = perf_event__process_build_id,
                         .id_index        = perf_event__process_id_index,
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index d309f4535a45..11290b57ce04 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -34,8 +34,9 @@
 #include "trace-event.h"
 #include "util/parse-events.h"
 #include "util/bpf-loader.h"
+#include "syscalltbl.h"
 
-#include <libaudit.h>
+#include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */
 #include <stdlib.h>
 #include <sys/mman.h>
 #include <linux/futex.h>
@@ -112,6 +113,56 @@
 # define PERF_FLAG_FD_CLOEXEC           (1UL << 3) /* O_CLOEXEC */
 #endif
 
+struct trace {
+        struct perf_tool        tool;
+        struct syscalltbl       *sctbl;
+        struct {
+                int             max;
+                struct syscall  *table;
+                struct {
+                        struct perf_evsel *sys_enter,
+                                          *sys_exit;
+                }               events;
+        } syscalls;
+        struct record_opts      opts;
+        struct perf_evlist      *evlist;
+        struct machine          *host;
+        struct thread           *current;
+        u64                     base_time;
+        FILE                    *output;
+        unsigned long           nr_events;
+        struct strlist          *ev_qualifier;
+        struct {
+                size_t          nr;
+                int             *entries;
+        }                       ev_qualifier_ids;
+        struct intlist          *tid_list;
+        struct intlist          *pid_list;
+        struct {
+                size_t          nr;
+                pid_t           *entries;
+        }                       filter_pids;
+        double                  duration_filter;
+        double                  runtime_ms;
+        struct {
+                u64             vfs_getname,
+                                proc_getname;
+        } stats;
+        bool                    not_ev_qualifier;
+        bool                    live;
+        bool                    full_time;
+        bool                    sched;
+        bool                    multiple_threads;
+        bool                    summary;
+        bool                    summary_only;
+        bool                    show_comm;
+        bool                    show_tool_stats;
+        bool                    trace_syscalls;
+        bool                    force;
+        bool                    vfs_getname;
+        int                     trace_pgfaults;
+        int                     open_id;
+};
 
 struct tp_field {
         int offset;
@@ -1073,12 +1124,18 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
           .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \
           .arg_parm      = { [arg] = &strarray__##array, }
 
+#include "trace/beauty/pid.c"
+#include "trace/beauty/mode_t.c"
+#include "trace/beauty/sched_policy.c"
+#include "trace/beauty/waitid_options.c"
+
 static struct syscall_fmt {
         const char *name;
         const char *alias;
         size_t     (*arg_scnprintf[6])(char *bf, size_t size, struct syscall_arg *arg);
         void       *arg_parm[6];
         bool       errmsg;
+        bool       errpid;
         bool       timeout;
         bool       hexret;
 } syscall_fmts[] = {
@@ -1096,6 +1153,7 @@ static struct syscall_fmt {
         { .name     = "chroot",     .errmsg = true,
           .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
         { .name     = "clock_gettime",  .errmsg = true, STRARRAY(0, clk_id, clockid), },
+        { .name     = "clone",      .errpid = true, },
         { .name     = "close",      .errmsg = true,
           .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, },
         { .name     = "connect",    .errmsg = true, },
@@ -1161,6 +1219,9 @@ static struct syscall_fmt {
         { .name     = "getdents64", .errmsg = true,
           .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
         { .name     = "getitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
+        { .name     = "getpid",     .errpid = true, },
+        { .name     = "getpgid",    .errpid = true, },
+        { .name     = "getppid",    .errpid = true, },
         { .name     = "getrandom",  .errmsg = true,
           .arg_scnprintf = { [2] = SCA_GETRANDOM_FLAGS, /* flags */ }, },
         { .name     = "getrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
@@ -1304,6 +1365,8 @@ static struct syscall_fmt {
           .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
         { .name     = "rt_tgsigqueueinfo", .errmsg = true,
           .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
+        { .name     = "sched_setscheduler",   .errmsg = true,
+          .arg_scnprintf = { [1] = SCA_SCHED_POLICY, /* policy */ }, },
         { .name     = "seccomp", .errmsg = true,
           .arg_scnprintf = { [0] = SCA_SECCOMP_OP, /* op */
                              [1] = SCA_SECCOMP_FLAGS, /* flags */ }, },
@@ -1317,7 +1380,9 @@ static struct syscall_fmt {
         { .name     = "sendto",     .errmsg = true,
           .arg_scnprintf = { [0] = SCA_FD, /* fd */
                              [3] = SCA_MSG_FLAGS, /* flags */ }, },
+        { .name     = "set_tid_address", .errpid = true, },
         { .name     = "setitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
+        { .name     = "setpgid",    .errmsg = true, },
         { .name     = "setrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
         { .name     = "setxattr",   .errmsg = true,
           .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, },
@@ -1360,6 +1425,10 @@ static struct syscall_fmt {
           .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, },
         { .name     = "vmsplice",  .errmsg = true,
           .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
+        { .name     = "wait4",      .errpid = true,
+          .arg_scnprintf = { [2] = SCA_WAITID_OPTIONS, /* options */ }, },
+        { .name     = "waitid",     .errpid = true,
+          .arg_scnprintf = { [3] = SCA_WAITID_OPTIONS, /* options */ }, },
         { .name     = "write",      .errmsg = true,
           .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, },
         { .name     = "writev",     .errmsg = true,
@@ -1471,59 +1540,6 @@ fail:
 
 static const size_t trace__entry_str_size = 2048;
 
-struct trace {
-        struct perf_tool        tool;
-        struct {
-                int             machine;
-                int             open_id;
-        }                       audit;
-        struct {
-                int             max;
-                struct syscall  *table;
-                struct {
-                        struct perf_evsel *sys_enter,
-                                          *sys_exit;
-                }               events;
-        } syscalls;
-        struct record_opts      opts;
-        struct perf_evlist      *evlist;
-        struct machine          *host;
-        struct thread           *current;
-        u64                     base_time;
-        FILE                    *output;
-        unsigned long           nr_events;
-        struct strlist          *ev_qualifier;
-        struct {
-                size_t          nr;
-                int             *entries;
-        }                       ev_qualifier_ids;
-        struct intlist          *tid_list;
-        struct intlist          *pid_list;
-        struct {
-                size_t          nr;
-                pid_t           *entries;
-        }                       filter_pids;
-        double                  duration_filter;
-        double                  runtime_ms;
-        struct {
-                u64             vfs_getname,
-                                proc_getname;
-        } stats;
-        bool                    not_ev_qualifier;
-        bool                    live;
-        bool                    full_time;
-        bool                    sched;
-        bool                    multiple_threads;
-        bool                    summary;
-        bool                    summary_only;
-        bool                    show_comm;
-        bool                    show_tool_stats;
-        bool                    trace_syscalls;
-        bool                    force;
-        bool                    vfs_getname;
-        int                     trace_pgfaults;
-};
-
 static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
 {
         struct thread_trace *ttrace = thread__priv(thread);
@@ -1749,6 +1765,10 @@ static int syscall__set_arg_fmts(struct syscall *sc)
                         sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx];
                 else if (field->flags & FIELD_IS_POINTER)
                         sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex;
+                else if (strcmp(field->type, "pid_t") == 0)
+                        sc->arg_scnprintf[idx] = SCA_PID;
+                else if (strcmp(field->type, "umode_t") == 0)
+                        sc->arg_scnprintf[idx] = SCA_MODE_T;
                 ++idx;
         }
 
@@ -1759,7 +1779,7 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 {
         char tp_name[128];
         struct syscall *sc;
-        const char *name = audit_syscall_to_name(id, trace->audit.machine);
+        const char *name = syscalltbl__name(trace->sctbl, id);
 
         if (name == NULL)
                 return -1;
@@ -1834,7 +1854,7 @@ static int trace__validate_ev_qualifier(struct trace *trace)
 
         strlist__for_each(pos, trace->ev_qualifier) {
                 const char *sc = pos->s;
-                int id = audit_name_to_syscall(sc, trace->audit.machine);
+                int id = syscalltbl__id(trace->sctbl, sc);
 
                 if (id < 0) {
                         if (err == 0) {
@@ -2116,7 +2136,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 
         ret = perf_evsel__sc_tp_uint(evsel, ret, sample);
 
-        if (id == trace->audit.open_id && ret >= 0 && ttrace->filename.pending_open) {
+        if (id == trace->open_id && ret >= 0 && ttrace->filename.pending_open) {
                 trace__set_fd_pathname(thread, ret, ttrace->filename.name);
                 ttrace->filename.pending_open = false;
                 ++trace->stats.vfs_getname;
@@ -2147,7 +2167,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
         if (sc->fmt == NULL) {
 signed_print:
                 fprintf(trace->output, ") = %ld", ret);
-        } else if (ret < 0 && sc->fmt->errmsg) {
+        } else if (ret < 0 && (sc->fmt->errmsg || sc->fmt->errpid)) {
                 char bf[STRERR_BUFSIZE];
                 const char *emsg = strerror_r(-ret, bf, sizeof(bf)),
                            *e = audit_errno_to_name(-ret);
@@ -2157,7 +2177,16 @@ signed_print:
                 fprintf(trace->output, ") = 0 Timeout");
         else if (sc->fmt->hexret)
                 fprintf(trace->output, ") = %#lx", ret);
-        else
+        else if (sc->fmt->errpid) {
+                struct thread *child = machine__find_thread(trace->host, ret, ret);
+
+                if (child != NULL) {
+                        fprintf(trace->output, ") = %ld", ret);
+                        if (child->comm_set)
+                                fprintf(trace->output, " (%s)", thread__comm_str(child));
+                        thread__put(child);
+                }
+        } else
                 goto signed_print;
 
         fputc('\n', trace->output);
@@ -3159,10 +3188,6 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
                 NULL
         };
         struct trace trace = {
-                .audit = {
-                        .machine = audit_detect_machine(),
-                        .open_id = audit_name_to_syscall("open", trace.audit.machine),
-                },
                 .syscalls = {
                         . max = -1,
                 },
@@ -3237,8 +3262,9 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
         signal(SIGFPE, sighandler_dump_stack);
 
         trace.evlist = perf_evlist__new();
+        trace.sctbl = syscalltbl__new();
 
-        if (trace.evlist == NULL) {
+        if (trace.evlist == NULL || trace.sctbl == NULL) {
                 pr_err("Not enough memory to run!\n");
                 err = -ENOMEM;
                 goto out;
@@ -3276,6 +3302,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
                 }
         }
 
+        trace.open_id = syscalltbl__id(trace.sctbl, "open");
+
         if (ev_qualifier_str != NULL) {
                 const char *s = ev_qualifier_str;
                 struct strlist_config slist_config = {
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index f7d7f5a1cad5..1e46277286c2 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -27,7 +27,7 @@ NO_PERF_REGS := 1
 ifeq ($(ARCH),x86)
   $(call detected,CONFIG_X86)
   ifeq (${IS_64_BIT}, 1)
-    CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT
+    CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT -DHAVE_SYSCALL_TABLE -I$(OUTPUT)arch/x86/include/generated
     ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
     LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
     $(call detected,CONFIG_X86_64)
@@ -268,6 +268,12 @@ else
     ifneq ($(feature-dwarf), 1)
       msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
       NO_DWARF := 1
+    else
+      ifneq ($(feature-dwarf_getlocations), 1)
+        msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157);
+      else
+        CFLAGS += -DHAVE_DWARF_GETLOCATIONS
+      endif # dwarf_getlocations
     endif # Dwarf support
   endif # libelf support
 endif # NO_LIBELF
@@ -289,9 +295,6 @@ ifndef NO_LIBELF
     CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT
   endif
 
-  # include ARCH specific config
-  -include $(src-perf)/arch/$(ARCH)/Makefile
-
   ifndef NO_DWARF
     ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
       msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled);
diff --git a/tools/perf/trace/beauty/mode_t.c b/tools/perf/trace/beauty/mode_t.c
new file mode 100644
index 000000000000..930d8fef2400
--- /dev/null
+++ b/tools/perf/trace/beauty/mode_t.c
@@ -0,0 +1,68 @@
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+/* From include/linux/stat.h */
+#ifndef S_IRWXUGO
+#define S_IRWXUGO       (S_IRWXU|S_IRWXG|S_IRWXO)
+#endif
+#ifndef S_IALLUGO
+#define S_IALLUGO       (S_ISUID|S_ISGID|S_ISVTX|S_IRWXUGO)
+#endif
+#ifndef S_IRUGO
+#define S_IRUGO         (S_IRUSR|S_IRGRP|S_IROTH)
+#endif
+#ifndef S_IWUGO
+#define S_IWUGO         (S_IWUSR|S_IWGRP|S_IWOTH)
+#endif
+#ifndef S_IXUGO
+#define S_IXUGO         (S_IXUSR|S_IXGRP|S_IXOTH)
+#endif
+
+static size_t syscall_arg__scnprintf_mode_t(char *bf, size_t size, struct syscall_arg *arg)
+{
+        int printed = 0, mode = arg->val;
+
+#define P_MODE(n) \
+        if ((mode & S_##n) == S_##n) { \
+                printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+                mode &= ~S_##n; \
+        }
+
+        P_MODE(IALLUGO);
+        P_MODE(IRWXUGO);
+        P_MODE(IRUGO);
+        P_MODE(IWUGO);
+        P_MODE(IXUGO);
+        P_MODE(IFMT);
+        P_MODE(IFSOCK);
+        P_MODE(IFLNK);
+        P_MODE(IFREG);
+        P_MODE(IFBLK);
+        P_MODE(IFDIR);
+        P_MODE(IFCHR);
+        P_MODE(IFIFO);
+        P_MODE(ISUID);
+        P_MODE(ISGID);
+        P_MODE(ISVTX);
+        P_MODE(IRWXU);
+        P_MODE(IRUSR);
+        P_MODE(IWUSR);
+        P_MODE(IXUSR);
+        P_MODE(IRWXG);
+        P_MODE(IRGRP);
+        P_MODE(IWGRP);
+        P_MODE(IXGRP);
+        P_MODE(IRWXO);
+        P_MODE(IROTH);
+        P_MODE(IWOTH);
+        P_MODE(IXOTH);
+#undef P_MODE
+
+        if (mode)
+                printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", mode);
+
+        return printed;
+}
+
+#define SCA_MODE_T syscall_arg__scnprintf_mode_t
diff --git a/tools/perf/trace/beauty/pid.c b/tools/perf/trace/beauty/pid.c
new file mode 100644
index 000000000000..111ae08d38f1
--- /dev/null
+++ b/tools/perf/trace/beauty/pid.c
@@ -0,0 +1,18 @@
+static size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_arg *arg)
+{
+        int pid = arg->val;
+        struct trace *trace = arg->trace;
+        size_t printed = scnprintf(bf, size, "%d", pid);
+        struct thread *thread = machine__find_thread(trace->host, pid, pid);
+
+        if (thread != NULL) {
+                if (thread->comm_set)
+                        printed += scnprintf(bf + printed, size - printed,
+                                             " (%s)", thread__comm_str(thread));
+                thread__put(thread);
+        }
+
+        return printed;
+}
+
+#define SCA_PID syscall_arg__scnprintf_pid
diff --git a/tools/perf/trace/beauty/sched_policy.c b/tools/perf/trace/beauty/sched_policy.c
new file mode 100644
index 000000000000..c205bc608b3c
--- /dev/null
+++ b/tools/perf/trace/beauty/sched_policy.c
@@ -0,0 +1,44 @@
+#include <sched.h>
+
+/*
+ * Not defined anywhere else, probably, just to make sure we
+ * catch future flags
+ */
+#define SCHED_POLICY_MASK 0xff
+
+#ifndef SCHED_DEADLINE
+#define SCHED_DEADLINE 6
+#endif
+
+static size_t syscall_arg__scnprintf_sched_policy(char *bf, size_t size,
+                                                  struct syscall_arg *arg)
+{
+        const char *policies[] = {
+                "NORMAL", "FIFO", "RR", "BATCH", "ISO", "IDLE", "DEADLINE",
+        };
+        size_t printed;
+        int policy = arg->val,
+            flags = policy & ~SCHED_POLICY_MASK;
+
+        policy &= SCHED_POLICY_MASK;
+        if (policy <= SCHED_DEADLINE)
+                printed = scnprintf(bf, size, "%s", policies[policy]);
+        else
+                printed = scnprintf(bf, size, "%#x", policy);
+
+#define P_POLICY_FLAG(n) \
+        if (flags & SCHED_##n) { \
+                printed += scnprintf(bf + printed, size - printed, "|%s", #n); \
+                flags &= ~SCHED_##n; \
+        }
+
+        P_POLICY_FLAG(RESET_ON_FORK);
+#undef P_POLICY_FLAG
+
+        if (flags)
+                printed += scnprintf(bf + printed, size - printed, "|%#x", flags);
+
+        return printed;
+}
+
+#define SCA_SCHED_POLICY syscall_arg__scnprintf_sched_policy
diff --git a/tools/perf/trace/beauty/waitid_options.c b/tools/perf/trace/beauty/waitid_options.c
new file mode 100644
index 000000000000..7942724adec8
--- /dev/null
+++ b/tools/perf/trace/beauty/waitid_options.c
@@ -0,0 +1,26 @@
+#include <sys/types.h>
+#include <sys/wait.h>
+
+static size_t syscall_arg__scnprintf_waitid_options(char *bf, size_t size,
+                                                    struct syscall_arg *arg)
+{
+        int printed = 0, options = arg->val;
+
+#define P_OPTION(n) \
+        if (options & W##n) { \
+                printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+                options &= ~W##n; \
+        }
+
+        P_OPTION(NOHANG);
+        P_OPTION(UNTRACED);
+        P_OPTION(CONTINUED);
+#undef P_OPTION
+
+        if (options)
+                printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", options);
+
+        return printed;
+}
+
+#define SCA_WAITID_OPTIONS syscall_arg__scnprintf_waitid_options
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 2a83414159a6..e70df2e54d66 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1607,9 +1607,8 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 
                         ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
                         dummy_hpp.buf[ret] = '\0';
-                        rtrim(dummy_hpp.buf);
 
-                        start = ltrim(dummy_hpp.buf);
+                        start = trim(dummy_hpp.buf);
                         ret = strlen(start);
 
                         if (start != dummy_hpp.buf)
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 7aff5acf3265..560eb47d56f9 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -569,9 +569,8 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
                         first_col = false;
 
                         fmt->header(fmt, hpp, hists_to_evsel(hists));
-                        rtrim(hpp->buf);
 
-                        header_width += fprintf(fp, "%s", ltrim(hpp->buf));
+                        header_width += fprintf(fp, "%s", trim(hpp->buf));
                 }
         }
 
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 85ceff357769..ea4ac03c1ec8 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -38,6 +38,7 @@ libperf-y += machine.o
 libperf-y += map.o
 libperf-y += pstack.o
 libperf-y += session.o
+libperf-$(CONFIG_AUDIT) += syscalltbl.o
 libperf-y += ordered-events.o
 libperf-y += comm.o
 libperf-y += thread.o
@@ -147,6 +148,10 @@ CFLAGS_libstring.o     += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ET
 CFLAGS_hweight.o       += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_parse-events.o  += -Wno-redundant-decls
 
+$(OUTPUT)util/syscalltbl.o: util/syscalltbl.c arch/x86/entry/syscalls/syscall_64.tbl $(OUTPUT)arch/x86/include/generated/asm/syscalls_64.c FORCE
+        $(call rule_mkdir)
+        $(call if_changed_dep,cc_o_c)
+
 $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE
         $(call rule_mkdir)
         $(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 5c20d783423b..664490b8b327 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -381,11 +381,11 @@ static int perf_buildid_config(const char *var, const char *value)
 {
         /* same dir for all commands */
         if (!strcmp(var, "buildid.dir")) {
-                const char *dirname = perf_config_dirname(var, value);
+                const char *dir = perf_config_dirname(var, value);
 
-                if (!dirname)
+                if (!dir)
                         return -1;
-                strncpy(buildid_dir, dirname, MAXPATHLEN-1);
+                strncpy(buildid_dir, dir, MAXPATHLEN-1);
                 buildid_dir[MAXPATHLEN-1] = '\0';
         }
 
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 577e600c8eb1..aea189b41cc8 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -959,6 +959,7 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
         return 0;
 }
 
+#ifdef HAVE_DWARF_GETLOCATIONS
 /**
  * die_get_var_innermost_scope - Get innermost scope range of given variable DIE
  * @sp_die: a subprogram DIE
@@ -1080,3 +1081,11 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf)
 
         return ret;
 }
+#else
+int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
+                      Dwarf_Die *vr_die __maybe_unused,
+                      struct strbuf *buf __maybe_unused)
+{
+        return -ENOTSUP;
+}
+#endif
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 171b6d10a04b..02c31865648b 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -431,6 +431,13 @@ u64 map__rip_2objdump(struct map *map, u64 rip)
         if (map->dso->rel)
                 return rip - map->pgoff;
 
+        /*
+         * kernel modules also have DSO_TYPE_USER in dso->kernel,
+         * but all kernel modules are ET_REL, so won't get here.
+         */
+        if (map->dso->kernel == DSO_TYPE_USER)
+                return rip + map->dso->text_offset;
+
         return map->unmap_ip(map, rip) - map->reloc;
 }
 
@@ -454,6 +461,13 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
         if (map->dso->rel)
                 return map->unmap_ip(map, ip + map->pgoff);
 
+        /*
+         * kernel modules also have DSO_TYPE_USER in dso->kernel,
+         * but all kernel modules are ET_REL, so won't get here.
+         */
+        if (map->dso->kernel == DSO_TYPE_USER)
+                return map->unmap_ip(map, ip - map->dso->text_offset);
+
         return ip + map->reloc;
 }
 
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 1d160855cda9..35ed00a600fb 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -283,18 +283,27 @@ static SV *perl_process_callchain(struct perf_sample *sample,
                 if (!elem)
                         goto exit;
 
-                hv_stores(elem, "ip", newSVuv(node->ip));
+                if (!hv_stores(elem, "ip", newSVuv(node->ip))) {
+                        hv_undef(elem);
+                        goto exit;
+                }
 
                 if (node->sym) {
                         HV *sym = newHV();
-                        if (!sym)
+                        if (!sym) {
+                                hv_undef(elem);
+                                goto exit;
+                        }
+                        if (!hv_stores(sym, "start",   newSVuv(node->sym->start)) ||
+                            !hv_stores(sym, "end",     newSVuv(node->sym->end)) ||
+                            !hv_stores(sym, "binding", newSVuv(node->sym->binding)) ||
+                            !hv_stores(sym, "name",    newSVpvn(node->sym->name,
+                                                                node->sym->namelen)) ||
+                            !hv_stores(elem, "sym",    newRV_noinc((SV*)sym))) {
+                                hv_undef(sym);
+                                hv_undef(elem);
                                 goto exit;
-                        hv_stores(sym, "start",   newSVuv(node->sym->start));
-                        hv_stores(sym, "end",     newSVuv(node->sym->end));
-                        hv_stores(sym, "binding", newSVuv(node->sym->binding));
-                        hv_stores(sym, "name",    newSVpvn(node->sym->name,
-                                                           node->sym->namelen));
-                        hv_stores(elem, "sym",    newRV_noinc((SV*)sym));
+                        }
                 }
 
                 if (node->map) {
@@ -306,7 +315,10 @@ static SV *perl_process_callchain(struct perf_sample *sample,
                                 else if (map->dso->name)
                                         dsoname = map->dso->name;
                         }
-                        hv_stores(elem, "dso", newSVpv(dsoname,0));
+                        if (!hv_stores(elem, "dso", newSVpv(dsoname,0))) {
+                                hv_undef(elem);
+                                goto exit;
+                        }
                 }
 
                 callchain_cursor_advance(&callchain_cursor);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index bc229a74c6a9..3f9d6798bd18 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -709,17 +709,10 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
         if (ss->opdshdr.sh_type != SHT_PROGBITS)
                 ss->opdsec = NULL;
 
-        if (dso->kernel == DSO_TYPE_USER) {
-                GElf_Shdr shdr;
-                ss->adjust_symbols = (ehdr.e_type == ET_EXEC ||
-                                ehdr.e_type == ET_REL ||
-                                dso__is_vdso(dso) ||
-                                elf_section_by_name(elf, &ehdr, &shdr,
-                                                     ".gnu.prelink_undo",
-                                                     NULL) != NULL);
-        } else {
+        if (dso->kernel == DSO_TYPE_USER)
+                ss->adjust_symbols = true;
+        else
                 ss->adjust_symbols = elf__needs_adjust_symbols(ehdr);
-        }
 
         ss->name   = strdup(name);
         if (!ss->name) {
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
new file mode 100644
index 000000000000..bbb4c1957578
--- /dev/null
+++ b/tools/perf/util/syscalltbl.c
@@ -0,0 +1,134 @@
+/*
+ * System call table mapper
+ *
+ * (C) 2016 Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include "syscalltbl.h"
+#include <stdlib.h>
+
+#ifdef HAVE_SYSCALL_TABLE
+#include <linux/compiler.h>
+#include <string.h>
+#include "util.h"
+
+#if defined(__x86_64__)
+#include <asm/syscalls_64.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_x86_64_MAX_ID;
+static const char **syscalltbl_native = syscalltbl_x86_64;
+#endif
+
+struct syscall {
+        int id;
+        const char *name;
+};
+
+static int syscallcmpname(const void *vkey, const void *ventry)
+{
+        const char *key = vkey;
+        const struct syscall *entry = ventry;
+
+        return strcmp(key, entry->name);
+}
+
+static int syscallcmp(const void *va, const void *vb)
+{
+        const struct syscall *a = va, *b = vb;
+
+        return strcmp(a->name, b->name);
+}
+
+static int syscalltbl__init_native(struct syscalltbl *tbl)
+{
+        int nr_entries = 0, i, j;
+        struct syscall *entries;
+
+        for (i = 0; i <= syscalltbl_native_max_id; ++i)
+                if (syscalltbl_native[i])
+                        ++nr_entries;
+
+        entries = tbl->syscalls.entries = malloc(sizeof(struct syscall) * nr_entries);
+        if (tbl->syscalls.entries == NULL)
+                return -1;
+
+        for (i = 0, j = 0; i <= syscalltbl_native_max_id; ++i) {
+                if (syscalltbl_native[i]) {
+                        entries[j].name = syscalltbl_native[i];
+                        entries[j].id = i;
+                        ++j;
+                }
+        }
+
+        qsort(tbl->syscalls.entries, nr_entries, sizeof(struct syscall), syscallcmp);
+        tbl->syscalls.nr_entries = nr_entries;
+        return 0;
+}
+
+struct syscalltbl *syscalltbl__new(void)
+{
+        struct syscalltbl *tbl = malloc(sizeof(*tbl));
+        if (tbl) {
+                if (syscalltbl__init_native(tbl)) {
+                        free(tbl);
+                        return NULL;
+                }
+        }
+        return tbl;
+}
+
+void syscalltbl__delete(struct syscalltbl *tbl)
+{
+        zfree(&tbl->syscalls.entries);
+        free(tbl);
+}
+
+const char *syscalltbl__name(const struct syscalltbl *tbl __maybe_unused, int id)
+{
+        return id <= syscalltbl_native_max_id ? syscalltbl_native[id]: NULL;
+}
+
+int syscalltbl__id(struct syscalltbl *tbl, const char *name)
+{
+        struct syscall *sc = bsearch(name, tbl->syscalls.entries,
+                                     tbl->syscalls.nr_entries, sizeof(*sc),
+                                     syscallcmpname);
+
+        return sc ? sc->id : -1;
+}
+
+#else /* HAVE_SYSCALL_TABLE */
+
+#include <libaudit.h>
+
+struct syscalltbl *syscalltbl__new(void)
+{
+        struct syscalltbl *tbl = malloc(sizeof(*tbl));
+        if (tbl)
+                tbl->audit_machine = audit_detect_machine();
+        return tbl;
+}
+
+void syscalltbl__delete(struct syscalltbl *tbl)
+{
+        free(tbl);
+}
+
+const char *syscalltbl__name(const struct syscalltbl *tbl, int id)
+{
+        return audit_syscall_to_name(id, tbl->audit_machine);
+}
+
+int syscalltbl__id(struct syscalltbl *tbl, const char *name)
+{
+        return audit_name_to_syscall(name, tbl->audit_machine);
+}
+#endif /* HAVE_SYSCALL_TABLE */
diff --git a/tools/perf/util/syscalltbl.h b/tools/perf/util/syscalltbl.h
new file mode 100644
index 000000000000..e2951510484f
--- /dev/null
+++ b/tools/perf/util/syscalltbl.h
@@ -0,0 +1,20 @@
+#ifndef __PERF_SYSCALLTBL_H
+#define __PERF_SYSCALLTBL_H
+
+struct syscalltbl {
+        union {
+                int audit_machine;
+                struct {
+                        int nr_entries;
+                        void *entries;
+                } syscalls;
+        };
+};
+
+struct syscalltbl *syscalltbl__new(void);
+void syscalltbl__delete(struct syscalltbl *tbl);
+
+const char *syscalltbl__name(const struct syscalltbl *tbl, int id);
+int syscalltbl__id(struct syscalltbl *tbl, const char *name);
+
+#endif /* __PERF_SYSCALLTBL_H */
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index a0ac0317affb..e214207bb13a 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -9,6 +9,9 @@
 #include "symbol.h"
 #include <strlist.h>
 #include <intlist.h>
+#ifdef HAVE_LIBUNWIND_SUPPORT
+#include <libunwind.h>
+#endif
 
 struct thread_stack;
 
@@ -32,6 +35,9 @@ struct thread {
 
         void                    *priv;
         struct thread_stack     *ts;
+#ifdef HAVE_LIBUNWIND_SUPPORT
+        unw_addr_space_t        addr_space;
+#endif
 };
 
 struct machine;
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index ee7e372297e5..63687d3a344e 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -32,6 +32,7 @@
 #include "symbol.h"
 #include "util.h"
 #include "debug.h"
+#include "asm/bug.h"
 
 extern int
 UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
@@ -580,43 +581,33 @@ static unw_accessors_t accessors = {
 
 int unwind__prepare_access(struct thread *thread)
 {
-        unw_addr_space_t addr_space;
-
         if (callchain_param.record_mode != CALLCHAIN_DWARF)
                 return 0;
 
-        addr_space = unw_create_addr_space(&accessors, 0);
-        if (!addr_space) {
+        thread->addr_space = unw_create_addr_space(&accessors, 0);
+        if (!thread->addr_space) {
                 pr_err("unwind: Can't create unwind address space.\n");
                 return -ENOMEM;
         }
 
-        unw_set_caching_policy(addr_space, UNW_CACHE_GLOBAL);
-        thread__set_priv(thread, addr_space);
-
+        unw_set_caching_policy(thread->addr_space, UNW_CACHE_GLOBAL);
         return 0;
 }
 
 void unwind__flush_access(struct thread *thread)
 {
-        unw_addr_space_t addr_space;
-
         if (callchain_param.record_mode != CALLCHAIN_DWARF)
                 return;
 
-        addr_space = thread__priv(thread);
-        unw_flush_cache(addr_space, 0, 0);
+        unw_flush_cache(thread->addr_space, 0, 0);
 }
 
 void unwind__finish_access(struct thread *thread)
 {
-        unw_addr_space_t addr_space;
-
         if (callchain_param.record_mode != CALLCHAIN_DWARF)
                 return;
 
-        addr_space = thread__priv(thread);
-        unw_destroy_addr_space(addr_space);
+        unw_destroy_addr_space(thread->addr_space);
 }
 
 static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
@@ -639,7 +630,9 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
          * unwind itself.
          */
         if (max_stack - 1 > 0) {
-                addr_space = thread__priv(ui->thread);
+                WARN_ONCE(!ui->thread, "WARNING: ui->thread is NULL");
+                addr_space = ui->thread->addr_space;
+
                 if (addr_space == NULL)
                         return -1;
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 8298d607c738..3bf3de86d429 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -254,6 +254,11 @@ int hex2u64(const char *ptr, u64 *val);
 char *ltrim(char *s);
 char *rtrim(char *s);
 
+static inline char *trim(char *s)
+{
+        return ltrim(rtrim(s));
+}
+
 void dump_stack(void);
 void sighandler_dump_stack(int sig);